© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 79542
    Prev
    Next
    INDEX
    Explanations

    references to strategies and solutions related to policy or scientific approaches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ī
    -0.07
    :frame
    -0.07
    pras
    -0.06
    icont
    -0.06
    lesi
    -0.06
     conduit
    -0.06
    orer
    -0.06
    amas
    -0.06
    occasion
    -0.06
     phục
    -0.06
    POSITIVE LOGITS
     options
    0.11
     alternatives
    0.11
     option
    0.09
     possibilities
    0.09
    options
    0.09
     Options
    0.08
    Options
    0.08
     alternative
    0.08
    -options
    0.08
     solutions
    0.07
    Activations Density 0.042%

    No Known Activations